maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[InstCombine] avoid infinite loop from shuffle-extract-insert sequence (PR30923) 

Removing the limitation in visitInsertElementInst() causes several regressions
because we're not prepared to fold sequences of shuffles or inserts and extracts
separated by shuffles. Fixing that appears to be a difficult mission because we
are purposely trying to avoid creating shuffles with arbitrary shuffle masks
because some targets may choke on those.

https://llvm.org/bugs/show_bug.cgi?id=30923

llvm-svn: 286423
This commit is contained in:
Sanjay Patel 2016-11-10 00:15:14 +00:00
parent 35e007515f
commit 4e1b5a53c7
2 changed files with 35 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
llvm/lib/Transforms/InstCombine/InstCombineVectorOps.cpp
View File

@ -413,6 +413,14 @@ static void replaceExtractElements(InsertElementInst *InsElt,
if (InsertionBlock != InsElt->getParent())
return;
// TODO: This restriction matches the check in visitInsertElementInst() and
// prevents an infinite loop caused by not turning the extract/insert pair
// into a shuffle. We really should not need either check, but we're lacking
// folds for shufflevectors because we're afraid to generate shuffle masks
// that the backend can't handle.
if (InsElt->hasOneUse() && isa<InsertElementInst>(InsElt->user_back()))
return;
auto *WideVec = new ShuffleVectorInst(ExtVecOp, UndefValue::get(ExtVecType),
ConstantVector::get(ExtendMask));

27
llvm/test/Transforms/InstCombine/insert-extract-shuffle.ll
View File

@ -237,3 +237,30 @@ end:
ret double %mu
}
; https://llvm.org/bugs/show_bug.cgi?id=30923
; Delete the widening shuffle if we're not going to reduce the extract/insert to a shuffle.
define <4 x float> @PR30923(<2 x float> %x) {
; CHECK-LABEL: @PR30923(
; CHECK-NEXT: bb1:
; CHECK-NEXT: [[EXT1:%.*]] = extractelement <2 x float> %x, i32 1
; CHECK-NEXT: store float [[EXT1]], float* undef, align 4
; CHECK-NEXT: br label %bb2
; CHECK: bb2:
; CHECK-NEXT: [[EXT2:%.*]] = extractelement <2 x float> %x, i32 0
; CHECK-NEXT: [[INS1:%.*]] = insertelement <4 x float> <float 0.000000e+00, float 0.000000e+00, float undef, float undef>, float [[EXT2]], i32 2
; CHECK-NEXT: [[INS2:%.*]] = insertelement <4 x float> [[INS1]], float [[EXT1]], i32 3
; CHECK-NEXT: ret <4 x float> [[INS2]]
;
bb1:
%ext1 = extractelement <2 x float> %x, i32 1
store float %ext1, float* undef, align 4
br label %bb2
bb2:
%widen = shufflevector <2 x float> %x, <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
%ext2 = extractelement <4 x float> %widen, i32 0
%ins1 = insertelement <4 x float> <float 0.0, float 0.0, float undef, float undef>, float %ext2, i32 2
%ins2 = insertelement <4 x float> %ins1, float %ext1, i32 3
ret <4 x float> %ins2
}